STAT302 Secs 102 103 Summer I 1998 Exam 3 Form A Instructor Julie Hagen Carroll 1 Don t even open this until you are told to do so 2 Be sure to mark your section number 102 or 103 and your test form A or B on the scantron 3 Sign your name where indicated on your scantron and write your Wednesday section number and computer number beside it Also you must place your scantron in the correct section stack for next Wednesday 4 There are 20 multiple choice questions on this exam each worth 5 points There is partial credit Please mark your answers clearly on the scantron Multiple marks will be counted wrong 5 You will have 60 minutes to finish this exam 6 If you are caught cheating or helping someone to cheat on this exam you both will receive a grade of zero on the exam You must work alone 7 This exam is worth 100 points and will constitute 20 of your final grade 8 Good luck 1 STAT302 102 103 Exam 3 Form A Summer 1998 3 What would be the consequence of making a Type II error in the situation above A You claim that Aggie first year graduates make more than t sips when they do not make more B You do not claim that Aggie first year graduates make more than t sips when they do not make more C You claim that Aggie first year graduates make more than t sips when they do make more D You do not claim that Aggie first year graduates make more than t sips when they do make more E You claim that Rice Owls make the most money 1 What are H0 and HA for the graph above A B C D E H0 H0 H0 H0 H0 4 If t u found out about your hypothesis test before you collected any data which level would they want you to use Assume that they don t want you to conclude that Aggies make more money 1 2 vs HA 1 6 2 1 0 vs HA 1 6 0 1 0 vs HA 2 0 0 vs HA 6 0 1 2 vs HA 1 2 A B C D 0 01 0 05 0 10 It doesn t matter since we know that Aggies make more E They don t care since they don t understand hypothesis testing 2 Suppose you feel certain that for the last 10 years Aggie graduates made more money than t sips in their first year out of college Which of the following would be the best method for testing this hypothesis A Ask 10 Aggies and 10 t sips how much they make and compare the averages B Collect random samples of graduating seniors from both schools and compare their average job offers C Collect random samples of people who graduated in the last 10 years from both schools and compare the proportions of salaries over 30 000 for each school D Collect random samples of people who graduated in the last 10 years from both schools and compare their average starting salaries E Collect random samples of graduating seniors from both schools and compare the proportions of salaries over 30 000 for each school 5 Still talking about Aggies and t sips and salaries which type test case should you use if you don t know anything about the means or the standard deviations of either school A Case 1 because it is the most basic type of test B Case 3 because we don t know that the data is normal nor the standard deviation C Case 6 because comparing the proportions would mean we don t have to have the same sample sizes D Case 9 because we don t know that the data is normal nor either standard deviation or even if they re equal E Case 11 because we should compare two proportions 2 STAT302 102 103 Exam 3 Form A Summer 1998 6 Ok suppose that the true mean starting salary for Aggies is 40 000 with a standard deviation of 1500 and that of t sips is 30 000 and 2000 respectively What is the distribution of the difference in sample means based on samples of size 100 A B C D E N 10 000 52 N 10 000 5002 N 10 000 2502 N 10 000 25002 N 70 000 5002 7 What is the significance level A the probability of rejecting the null hypothesis B a measure of how willing we are to make a Type I error C the proportion of times we will reject a true H0 D all of the above E exactly two of the above excluding D 9 If we had calculated 90 95 and 99 confidence intervals using the data above which of the following would be true A 0 would be in all three confidence intervals B 25 would be in all three confidence intervals C 25 would not be in any of the three confidence intervals D 25 would not be in the 90 or 95 but it would fall within the 99 confidence interval E 0 would not be in the 90 or 95 but it would fall within the 99 confidence interval 8 Suppose we generate 50 random samples from a population of N 4 102 From these samples we create 50 95 confidence intervals If we look at all of our confidence intervals collectively then A no more than 95 of them will contain the true mean of 4 B exactly 95 of them will contain the true mean of 4 C approximately 95 of them will contain the true mean of 4 D approximately 95 of them will contain the sample mean x E Exactly twoof the above are correct 10 Suppose we know that we rejected at the 5 level Which of the following do we also know A We would have also rejected at the 1 level B We don t know if we would have rejected at the 10 level C The hypothesized value e g 0 would be in a 95 confidence interval for D All of the above would be true E None of the above would be true 3 STAT302 102 103 Exam 3 Form A 11 Suppose we tested H0 50 vs HA 50 The p value for our sample was 0 026 Which of the following is the best definition of what the p value is saying 13 Suppose you are testing the hypothesis H0 3 vs HA 6 3 at 0 10 and the only information available from a sample of size n 10 from a normally distributed population is the 90 confidence interval 2 73 3 17 Then A There is 2 6 likelihood of getting a sample mean at least as large as our sample mean even though the true population mean is 50 B There is 2 6 likelihood of getting a sample mean at least as small as our sample mean even though the true population mean is 50 C There is 2 6 likelihood of getting the same sample …